Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.8690. Min Act: -0.1700
Data Index: 2949643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7439. Min Act: -0.1700
Data Index: 542801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7439. Min Act: -0.1700
Data Index: 5358364 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 6417289 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 2779204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 2192420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 5559258 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7439. Min Act: -0.1700
Data Index: 5067480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 7822634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 7119927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.7126. Min Act: -0.1700
Data Index: 731260 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 4152878 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 5338620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 1209592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 3542814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 945516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 2378982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 5938168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 2914591 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8690. Min Range: -3.8690
Max Act: 3.6814. Min Act: -0.1700
Data Index: 3032505 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19